U.S. patent application number 16/860165 was filed with the patent office on 2020-12-24 for information processing apparatus, information processing method, storage medium, and information processing system.
This patent application is currently assigned to Bridgestone Sports Co., Ltd.. The applicant listed for this patent is Bridgestone Sports Co., Ltd.. Invention is credited to Takuichi SHIMIZU, Hiroo Takagi.
Application Number | 20200398120 16/860165 |
Document ID | / |
Family ID | 1000004815290 |
Filed Date | 2020-12-24 |
![](/patent/app/20200398120/US20200398120A1-20201224-D00000.png)
![](/patent/app/20200398120/US20200398120A1-20201224-D00001.png)
![](/patent/app/20200398120/US20200398120A1-20201224-D00002.png)
![](/patent/app/20200398120/US20200398120A1-20201224-D00003.png)
![](/patent/app/20200398120/US20200398120A1-20201224-D00004.png)
![](/patent/app/20200398120/US20200398120A1-20201224-D00005.png)
![](/patent/app/20200398120/US20200398120A1-20201224-D00006.png)
![](/patent/app/20200398120/US20200398120A1-20201224-D00007.png)
![](/patent/app/20200398120/US20200398120A1-20201224-D00008.png)
![](/patent/app/20200398120/US20200398120A1-20201224-D00009.png)
![](/patent/app/20200398120/US20200398120A1-20201224-D00010.png)
United States Patent
Application |
20200398120 |
Kind Code |
A1 |
SHIMIZU; Takuichi ; et
al. |
December 24, 2020 |
INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD,
STORAGE MEDIUM, AND INFORMATION PROCESSING SYSTEM
Abstract
An apparatus includes an acquisition unit configured to acquire
a measurement result of a golf swing motion, and a calculation unit
configured to calculate a behavior of a shot by the golf swing
motion. The measurement result includes a head speed, an incident
angle, and a face angle at the time of striking. The behavior
includes an initial speed, a vertical launch angle, and a back spin
amount. The calculation unit calculates the behavior by
substituting the head speed, the incident angle, and the face
angle, all of which have been acquired by the acquisition unit,
into a predetermined arithmetic formula having a plurality of
variables including at least a head speed, an incident angle, and a
face angle at the time of striking of a golf club head.
Inventors: |
SHIMIZU; Takuichi;
(Chichibu-shi, JP) ; Takagi; Hiroo; (Chichibu-shi,
JP) |
|
Applicant: |
Name |
City |
State |
Country |
Type |
Bridgestone Sports Co., Ltd. |
Tokyo |
|
JP |
|
|
Assignee: |
Bridgestone Sports Co.,
Ltd.
Tokyo
JP
|
Family ID: |
1000004815290 |
Appl. No.: |
16/860165 |
Filed: |
April 28, 2020 |
Current U.S.
Class: |
1/1 |
Current CPC
Class: |
A63B 2220/35 20130101;
A63B 2220/16 20130101; A63B 53/0441 20200801; A63B 2225/02
20130101; A63B 53/04 20130101 |
International
Class: |
A63B 53/04 20060101
A63B053/04 |
Foreign Application Data
Date |
Code |
Application Number |
Jun 24, 2019 |
JP |
2019-116596 |
Claims
1. An information processing apparatus comprising: an acquisition
unit configured to acquire a measurement result of a golf swing
motion of a golfer; and a calculation unit configured to calculate
a behavior of a shot by the golf swing motion, wherein the
measurement result includes a head speed, an incident angle, and a
face angle at the time of striking of a golf club head, the
behavior of the shot includes an initial speed, a vertical launch
angle, and a back spin amount, and the calculation unit calculates
the behavior of the shot by substituting the head speed, the
incident angle, and the face angle, all of which have been acquired
by the acquisition unit, into a predetermined arithmetic formula
having a plurality of variables including at least a head speed, an
incident angle, and a face angle at the time of striking of a golf
club head.
2. The apparatus according to claim 1, further comprising a
selection unit configured to select a golf item suitable for the
golfer based on the behavior of the shot calculated by the
calculation unit.
3. The apparatus according to claim 1, wherein the behavior of the
shot further includes a horizontal launch angle and a side spin
amount.
4. The apparatus according to claim 1, wherein the arithmetic
formula is a formula derived from a first data group including the
measurement results of a plurality of golfers and a second data
group as actual measurement results of behaviors of shots by golf
swing motions of the plurality of golfers.
5. The apparatus according to claim 4, wherein the arithmetic
formula is a formula derived by machine learning using the first
data group and the second data group as supervised data.
6. The apparatus according to claim 1, wherein the measurement
result includes a striking position on a face surface of the golf
club head, the plurality of variables include a striking position
on a face surface of the golf club head, and the calculation unit
calculates the behavior of the shot by substituting, into the
arithmetic formula, the head speed, the incident angle, the face
angle, and the striking position, all of which have been acquired
by the acquisition unit.
7. The apparatus according to claim 1, wherein the acquisition unit
acquires an attribute of the golfer and an attribute of a golf item
used by the golfer in the golf swing motion, the plurality of
variables include an attribute of a golfer and an attribute of a
golf item, and the calculation unit calculates the behavior of the
shot by substituting, into the arithmetic formula, the head speed,
the incident angle, the face angle, the attribute of the golfer,
and the attribute of the golf item, all of which have been acquired
by the acquisition unit.
8. The apparatus according to claim 1, wherein the acquisition unit
acquires an attribute of the golfer, as the arithmetic formula,
there are a plurality of types of arithmetic formulas in
correspondence with attributes of golfers, and the calculation unit
selects an arithmetic formula for calculating the behavior of the
shot from the plurality of types of arithmetic formulas in
accordance with the attribute of the golfer acquired by the
acquisition unit.
9. The apparatus according to claim 1, wherein the acquisition unit
acquires an attribute of a golf item used by the golfer in the golf
swing motion, as the arithmetic formula, there are a plurality of
types of arithmetic formulas in correspondence with attributes of
golf items, and the calculation unit selects an arithmetic formula
for calculating the behavior of the shot from the plurality of
types of arithmetic formulas in accordance with the attribute of
the golf item acquired by the acquisition unit.
10. An information processing method comprising: causing a computer
to acquire a measurement result of a golf swing motion of a golfer;
and causing the computer to calculate a behavior of a shot by the
golf swing motion, wherein the measurement result includes a head
speed, an incident angle, and a face angle at the time of striking
of a golf club head, the behavior of the shot includes an initial
speed, a vertical launch angle, and a back spin amount, and in the
causing the computer to calculate the behavior of the shot, the
behavior of the shot is calculated by substituting the head speed,
the incident angle, and the face angle, all of which have been
acquired in the causing the computer to acquire the measurement
result, into a predetermined arithmetic formula having a plurality
of variables including at least a head speed, an incident angle,
and a face angle at the time of striking of a golf club head.
11. A storage medium storing a program for causing a computer to
function as an acquisition unit configured to acquire a measurement
result of a golf swing motion of a golfer, and a calculation unit
configured to calculate a behavior of a shot by the golf swing
motion, wherein the measurement result includes a head speed, an
incident angle, and a face angle at the time of striking of a golf
club head, the behavior of the shot includes an initial speed, a
vertical launch angle, and a back spin amount, and the calculation
unit calculates the behavior of the shot by substituting the head
speed, the incident angle, and the face angle, all of which have
been acquired by the acquisition unit, into a predetermined
arithmetic formula having a plurality of variables including at
least a head speed, an incident angle, and a face angle at the time
of striking of a golf club head.
12. An information processing system comprising: a measuring unit
configured to measure a golf swing motion of a golfer; an
acquisition unit configured to acquire a measurement result of the
measuring unit; and a calculation unit configured to calculate a
behavior of a shot by the golf swing motion, wherein the
measurement result includes a head speed, an incident angle, and a
face angle at the time of striking of a golf club head, the
behavior of the shot includes an initial speed, a vertical launch
angle, and a back spin amount, and the calculation unit calculates
the behavior of the shot by substituting the head speed, the
incident angle, and the face angle, all of which have been acquired
by the acquisition unit, into a predetermined arithmetic formula
having a plurality of variables including at least a head speed, an
incident angle, and a face angle at the time of striking of a golf
club head.
Description
CROSS-REFERENCE TO RELATED APPLICATION(S)
[0001] This application claims priority to and the benefit of
Japanese Patent Application No. 2019-116596 filed on Jun. 24, 2019,
the entire disclosure of which is incorporated herein by
reference.
BACKGROUND OF THE INVENTION
Field of the Invention
[0002] The present invention relates to an information processing
technique concerning behavior analysis in the golf field.
Description of the Related Art
[0003] There are various techniques for analyzing a swing motion of
a golfer. Japanese Patent Laid-Open No. 2017-023638 discloses a
technique of measuring the incident angle and the like of a golf
club head and analyzing a swing motion. Japanese Patent Laid-Open
No. 2017-023639 discloses a technique of measuring the rotation
angle and the like of a golf club and analyzing a swing motion.
Japanese Patent Laid-Open No. 2017-070366 discloses a technique of
estimating a striking position on a face surface at the time of
striking. Japanese Patent Laid-Open No. 2017-000179 discloses a
technique of analyzing the behavior of a golf club head and
predicting the ball flight of a shot. There is also proposed a
technique of recommending a golf item suitable for a golfer based
on such analysis result (for example, Japanese Patent Laid-Open No.
2011-015968).
[0004] The behavior of a shot such as the initial speed, launch
angle, and spin amount of a golf ball immediately after striking is
one of matters of high concern for a golfer. In general, the
behavior of a shot is actually measured by a measuring facility
such as a camera or a doppler radar. If there is no such measuring
facility, the golfer cannot know the behavior of a shot as a result
of his/her swing motion. Japanese Patent Laid-Open No. 2017-000179
proposes a technique of predicting the ball flight of a shot.
However, the technique predicts the behavior of a golf club head,
and analyzes a collision of the head with a golf ball, and thus
calculation is complicated.
SUMMARY OF THE INVENTION
[0005] The present invention has as its object to provide a
technique of estimating the behavior of a shot without requiring a
measuring facility such as a camera or a doppler radar.
[0006] According to an aspect of the present invention, there is
provided an information processing apparatus comprising: an
acquisition unit configured to acquire a measurement result of a
golf swing motion of a golfer; and a calculation unit configured to
calculate a behavior of a shot by the golf swing motion, wherein
the measurement result includes a head speed, an incident angle,
and a face angle at the time of striking of a golf club head, the
behavior of the shot includes an initial speed, a vertical launch
angle, and a back spin amount, and the calculation unit calculates
the behavior of the shot by substituting the head speed, the
incident angle, and the face angle, all of which have been acquired
by the acquisition unit, into a predetermined arithmetic formula
having a plurality of variables including at least a head speed, an
incident angle, and a face angle at the time of striking of a golf
club head.
[0007] Further features of the present invention will become
apparent from the following description of exemplary embodiments
(with reference to the attached drawings).
BRIEF DESCRIPTION OF THE DRAWINGS
[0008] FIG. 1 is a schematic view of an information processing
system according to an embodiment of the present invention;
[0009] FIG. 2A is an explanatory view of an incident angle;
[0010] FIG. 2B is an explanatory view of a face angle;
[0011] FIG. 3A is an explanatory view of distinction of a striking
position;
[0012] FIG. 3B is an explanatory view showing an example of a
method of measuring a striking position;
[0013] FIGS. 4A and 4B are explanatory views of the launch angles
of a shot;
[0014] FIGS. 5A and 5B are explanatory views of the spin amounts of
a shot;
[0015] FIGS. 5C and 5D are explanatory views of ball flight;
[0016] FIG. 6A is a flowchart illustrating an example of the
processing of a computer when generating an arithmetic formula by
performing machine learning;
[0017] FIG. 6B is a flowchart illustrating an example of the
processing of an information processing apparatus;
[0018] FIG. 7 is a view showing an example of a method of selecting
a recommended golf item;
[0019] FIGS. 8A and 8B are graphs each showing an example of a
method of selecting a recommended golf item;
[0020] FIG. 9 is a view showing examples of a plurality of kinds of
arithmetic formulas; and
[0021] FIG. 10 is a view showing another example of a system.
DESCRIPTION OF THE EMBODIMENTS
[0022] Hereinafter, embodiments will be described in detail with
reference to the attached drawings. Note that the following
embodiments are not intended to limit the scope of the claimed
invention, and limitation is not made an invention that requires
all combinations of features described in the embodiments. Two or
more of the multiple features described in the embodiments may be
combined as appropriate. Furthermore, the same reference numerals
are given to the same or similar configurations, and redundant
description thereof is omitted.
First Embodiment
[0023] <Arrangement of System>
[0024] FIG. 1 is a schematic view of an information processing
system 1 according to an embodiment of the present invention. The
system 1 includes a measuring apparatus 2, an information
processing apparatus 3, a display device 4, and an input device 5.
Arrows X, Y, and Z represent a three-dimensional coordinate system
recognized or set by the measuring apparatus 2. The arrows X and Y
represent horizontal directions orthogonal to each other, and the
arrow Z represents the vertical direction. The arrow X represents
the target line direction of a golf ball.
[0025] The measuring apparatus 2 is an apparatus that measures a
golf swing motion of a golfer 10. In this embodiment, the measuring
apparatus 2 is an apparatus that measures the behavior of a golf
club 100. The golf club 100 includes a head 101 having a face
surface (striking surface) 101a, and a shaft 102 connected to the
head 101. A grip (not shown) is attached to the end portion of the
shaft 102 on the side of the golfer 10. The measuring apparatus 2
is an apparatus attached to the shaft 102 (or grip) of the golf
club 100, and includes an acceleration sensor and an angular
velocity sensor. As the measuring apparatus 2, for example, TSND121
available from ATR-Promotions or M-tracer available from Seiko
Epson Corporation can be used. As a result of detection of the
measuring apparatus 2, time-series data of the three-dimensional
acceleration and three-dimensional angular velocity of the golf
club 100 during a swing are obtained.
[0026] The information processing apparatus 3 is a computer that
estimates, from the measurement result of the measuring apparatus 2
and the like, the behavior of a shot of a golf ball 200 struck by a
golf swing motion of the golfer 10 with the golf club 100. The
information processing apparatus according to this embodiment also
has a function of recommending a golf item suitable for the golfer
10 based on the estimated behavior of the shot. The golf item
includes a golf club or a golf ball. The information processing
apparatus 3 includes a processing unit 31, a storage unit 32, and
an I/F unit (interface unit) 33 which are electrically connected to
each other. The processing unit 31 is a processor such as a CPU.
The storage unit 32 includes one or a plurality of storage devices.
The storage devices are, for example, a RAM, a ROM, and a hard
disk. The storage unit 32 stores a program to be executed by the
processing unit 31, and various kinds of data. The program to be
executed by the processing unit 31 can be formed from a plurality
of instructions readable by the processing unit 31.
[0027] The I/F unit 33 inputs/outputs data between an external
device and the processing unit 31. The I/F unit 33 can include an
I/O interface and a communication interface. The measuring
apparatus 2 is communicably connected to the information processing
apparatus 3 by wired or wireless communication, and the measurement
result is acquired by the information processing apparatus 3.
[0028] The display device 4 and the input device 5 are connected to
the information processing apparatus 3. The display device 4 is,
for example, an electronic image display device such as a liquid
crystal display device, and displays the processing result of the
information processing apparatus 3. The input device 5 includes a
mouse and a keyboard, and accepts a data input and an operation
instruction for the information processing apparatus 3. The display
device 4 may be a device having an information input function like
a touch panel. In this case, the input device 5 need not be
provided.
[0029] <Estimation of Behavior of Shot>
[0030] The ball flight of the golf ball 200 struck by a golf swing
motion of the golfer 10 is important for him/her. The ball flight
of the golf ball is estimated based on the behavior of the shot
such as the initial speed, the vertical and horizontal launch
angles, the back spin amount, and the side spin amount of the golf
ball 200 immediately after striking. The behavior of the shot can
be actually measured by a measuring facility such as a camera or a
doppler radar. In this embodiment, however, the behavior of the
shot is estimated based on the measurement result of the measuring
apparatus 2 or the like without requiring any such measuring
facility.
[0031] <Generation of Arithmetic Formula>
[0032] In this embodiment, the behavior of the golf ball 200 is
estimated by an arithmetic formula (model) having the measurement
result of the golf swing motion of the golfer 10 and the like as
explanatory variables and the behavior of the golf ball 200
immediately after striking as a target variable. As an advance
preparation, an arithmetic formula is generated.
[0033] As the explanatory variables, the measurement result of the
golf swing motion of the golfer 10, the attributes of the golfer
10, and the attributes of a golf item can be used. The measurement
result of the golf swing motion can include a measurement result
obtained by the measuring apparatus 2 or another measurement
method. The measurement result obtained by the measuring apparatus
2 can include the head speed of the head 101 at the time of
striking, the incident angle of the head 101, and the face angle at
the time of striking. FIG. 2A is an explanatory view of the
incident angle, and FIG. 2B is an explanatory view of the face
angle.
[0034] Referring to FIG. 2A, the incident angle is the angle of the
trajectory of the head 101 in the Z direction at the time of
striking the golf ball 200 with respect to the X direction on the
X-Z plane. In an example shown in FIG. 2A, a direction D1 of the
head trajectory is specified based on the position of the head 101
a predetermined time before an impact timing and a position X1 of
the head 101 at the time of striking, and an angle .theta.1 between
the direction D1 and the X direction represents the incident angle.
In the example shown in FIG. 2A, the upward direction is set as the
positive direction, and the downward direction is set as the
negative direction. A striking timing can be measured by the
measuring apparatus 2 based on a change in acceleration of the golf
club 100. The position of the head 101 at this time corresponds to
the position X1 of the head 101 at the time of striking.
[0035] Referring to FIG. 2B, the face angle at the time of striking
is in the direction of the face surface 101a at the time of
striking the golf ball 200. In an example shown in FIG. 2B, an
angle .theta.2 formed by the Y direction and the face surface is
set as the face angle on the X-Y plane. In terms of measurement by
the measuring apparatus 2, the angle .theta.2 can be considered to
be a reference (0.degree.) at the time of calibration. For example,
calibration indicates processing of causing the measuring apparatus
2 to recognize a target direction. In the example shown in FIG. 2B,
an angle in a direction in which the face surface 101a is opened is
negative, and an angle in a direction in which the face surface is
closed is positive.
[0036] The measurement result of the measuring apparatus 2 can
additionally include a face rotation, a flexure return time, a loft
angle at the time of striking, and a swing trajectory. The face
rotation indicates a change degree of the face surface 101a during
a swing, and is, for example, a rotation amount around the axis of
the shaft 102 per unit time immediately before striking. The unit
time is, for example, 0.01 sec immediately before striking. The
flexure return time indicates a time from when the acceleration of
a predetermined portion (for example, the distal end portion of the
grip) of the golf club becomes maximum until an impact. In general,
during a golf swing, the shaft 102 has a tendency that it is
flexed, after a down swing, in a direction in which the head 101 is
behind the proximal end side, and decelerates on the proximal end
side before striking, and then the flexure of the shaft 102 returns
to reach an impact. The flexure return time can be regarded as a
time until the flexure of the shaft 102 returns before striking.
The loft angle at the time of striking indicates an angle between a
vertical plane and the face surface 101a at the time of striking on
the X-Z plane. The swing trajectory indicates the angle of the
trajectory of the head 101 in the Y direction at the time of
striking the golf ball 200 with respect to the X direction on the
X-Y plane.
[0037] The measurement result of the golf swing motion can
additionally include the striking position of the golf ball 200 on
the face surface 101a. FIG. 3A is an explanatory view showing an
example of digitization of the striking position. In an example
shown in FIG. 3A, a striking position 101b is specified in a
coordinate system in which the face center of the face surface 101a
is set as the origin, and a toe-heel direction D2 and a vertical
direction (crown-sole direction) D3 are set as coordinate axes. On
the coordinate axis D2, for example, a positive value is set on the
heel side. On the coordinate axis D3, for example, a positive value
is set on the upper side (crown side). The striking position 101b
can be measured by the measuring apparatus 2 based on the rotation
amount of the shaft 102 at the time of striking, a change in
direction of the face surface 101a, and the like. As shown in FIG.
3B, however, a marker 110 on which a striking mark of the golf ball
200 remains may be stuck on the face surface 101a, thereby
performing measurement. The face surface 101a and the position of
the golf ball 200 may be captured by a camera at the time of
striking, and the striking position may be measured from a captured
image.
[0038] The attributes of the golfer 10 can include the feature
amounts of the golfer such as the sex, height, weight, and age. The
attributes of the golf item can include the attributes of a golf
club and those of a golf ball. The attributes of the golf club can
include the feature amounts of the overall golf club, those of the
shaft, those of the head, and those of the grip. The feature
amounts of the overall golf club can include the total weight,
balance, and product type of the golf club. The feature amounts of
the shaft can include the length, rigidity, flex, torque, kick
point, and weight. The feature amounts of the head can include the
center-of-gravity depth, center-of-gravity height,
center-of-gravity distance, center-of-gravity angle, loft angle,
and weight. The feature amounts of the grip can include the weight
and material.
[0039] With respect to the target variable of the behavior of the
shot, the initial speed of the shot is the speed of the golf ball
200 immediately after striking. FIG. 4A is an explanatory view of
the vertical launch angle, and FIG. 4B is an explanatory view of
the horizontal launch angle. As shown in FIG. 4A, the vertical
launch angle is an angle .theta.3 of the trajectory of the golf
ball 200 in the Z direction immediately after striking with respect
to the X direction on the X-Z plane. A position X2 indicates the
initial position of the golf ball 200. In an example shown in FIG.
4A, the upper direction is set as the positive direction and the
lower direction is set as the negative direction. As shown in FIG.
4B, the horizontal launch angle is an angle .theta.4 of the
trajectory of the golf ball 200 in the Y direction immediately
after striking with respect to the Y direction on the X-Y plane. In
an example shown in FIG. 4B, the left direction is set as the
positive direction and the right direction is set as the negative
direction.
[0040] FIG. 5A is an explanatory view of the back spin amount. The
back spin amount is the rotation amount of the golf ball 200 around
the Y-axis immediately after striking. In an example shown in FIG.
5A, rotation in the upper direction is positive and rotation in the
lower direction is negative. FIG. 5B is an explanatory view of the
side spin amount. The side spin amount is the rotation amount of
the golf ball 200 around the Z-axis immediately after striking. In
an example shown in FIG. 5B, rotation in the hook direction is
positive, and rotation in the slice direction is negative.
[0041] An arithmetic formula can be generated using an actual
measured data group formed from an actual measured data group of
the target variable corresponding to the above-described data group
of the explanatory variables. The target variable is actually
measured by the measuring facility such as a camera or a doppler
radar. For example, TRACKMAN available from TRACKMAN can be
used.
[0042] The arithmetic formula can be derived by, for example,
machine learning using the actual measured data group as supervised
data. FIG. 6A is a flowchart illustrating an example of the
processing of a computer when deriving an arithmetic formula by
performing machine learning on the computer. The computer used for
machine learning may be the information processing apparatus 3 on
which machine learning software is installed.
[0043] In step S1, the actual measured data group is loaded as
supervised data. The actual measured data group can be accumulated
in advance in an external storage device in a predetermined data
format. In step S2, various settings of a learning method are made,
and machine learning is executed based on the supervised data
loaded in step S1. In step S3, an arithmetic formula is generated
as a product. The generated arithmetic formula is stored in the
storage unit 32 of the information processing apparatus 3, and used
to estimate the behavior of the shot.
[0044] Examples of an algorithm of machine learning are linear
regression using stochastic gradient descent, ridge regression,
lasso regression, support vector regression, and deep learning. For
linear regression using stochastic gradient descent, ridge
regression, or lasso regression, when the target variable is
represented by y, the explanatory variable is represented by x, and
a coefficient is represented by a, a linear formula can be used as
the arithmetic formula, given by:
y1=a1x1+a2x2+a3x3 . . .
[0045] Then, the coefficient a is obtained by machine learning in
step S2, thereby completing the arithmetic formula. For lasso
regression or deep learning, the formula and the coefficients in
the formula can be obtained by machine learning in step S2. For
lasso regression, the type of explanatory variable used finally can
also be determined by machine learning.
[0046] According to an experiment related to this embodiment, if,
among the explanatory variables, especially the head speed, the
incident angle of the head, and the face angle at the time of
striking had high correlations with the behavior (the initial speed
of the ball, the vertical and horizontal launch angles, the back
spin amount, and the side spin amount) of the shot, and were used
as explanatory variables, predetermined accuracy could be obtained
with respect to estimation of the behavior of the shot. Therefore,
at least the head speed and the face angle at the time of striking
are adopted as explanatory variables. In this case, if the
arithmetic formula is set by the above linear formula, for
example,
initial speed of ball=a1head speed+a2incident angle+a3face
angle+a0
vertical launch angle=a11head speed+a12incident angle+a13face
angle+a10
[0047] Among the explanatory variables, the striking position also
has high correlation with the behavior (the initial speed of the
ball, the vertical and horizontal launch angles, the back spin
amount, and the side spin amount) of the shot, thereby improving
the estimation accuracy. In this case, if the arithmetic formula is
set by the above linear formula, for example,
side spin amount=a21head speed+a22incident angle+a23face
angle+a24striking position+a20
[0048] The explanatory variables used for the arithmetic formula
are not limited them, as a matter of course. All or some of the
attributes of the golfer or all or some of the attributes of the
golf item may be included. With respect to the target variable, if
the initial speed of the shot, the vertical launch angle, and the
back spin amount are provided, the ball flight can be estimated
accurately to some extent. If the horizontal launch angle and the
side spin amount are further added, it is also possible to estimate
the degree of left or right bending of the shot, thereby improving
the estimation accuracy of the ball flight.
[0049] Note that the arithmetic formula may be derived by a method
other than machine learning, for example, correlation analysis. For
example, the arithmetic formulas may be derived from the actual
measured data group by multiple regression analysis. For multiple
regression analysis, by representing a coefficient by b, the
arithmetic formulas can be given by:
initial speed of ball=head speed.times.(b0+b1incident angle+b2face
angle+b3 (striking position in direction D3).sup.2+(striking
position in direction D2).sup.2)
vertical launch angle=b11.times.incident angle+b12face
angle+b13striking position in direction D3+b10
back spin amount=b21incident angle+b22face angle+b23striking
position in direction D3+b20
horizontal launch angle=b31swing trajectory+b32face
angle+b33striking position in direction D3+b34striking position in
toe-heel direction
side spin amount=b41incident angle+b42swing trajectory+b43face
angle+b44striking position in direction D2
[0050] <Estimation Processing and Selection of Recommended
Item>
[0051] FIG. 6B shows an example of processing of estimating the
behavior of the shot using the arithmetic formula obtained in the
processing shown in FIG. 6A, and shows processing executed by the
processing unit 31 of the information processing apparatus 3. In
step S11, processing of accepting the explanatory variables to be
used to estimate the behavior of the shot of this time is
performed. More specifically, the measuring apparatus 2 is made to
measure the swing motion of the golfer. In this example, the golfer
10 actually strikes the golf ball 200 by the golf club 100, and the
measuring apparatus 2 measures the behavior of the golf club 100. A
measurement result is stored in the storage unit 32. An operator
can input the explanatory variables other than the measurement
result of the measuring apparatus 2 using the input device 5, and
the input contents are stored in the storage unit 32.
[0052] In step S12, the arithmetic formula stored in the storage
unit 32 is read out. In step S13, the explanatory variables to be
used for estimation of this time, which have been accepted in step
S11, are read out. In step S14, the explanatory variables read out
in step S13 are substituted into the arithmetic formula read out in
step S12, thereby calculating the target variable. This can obtain
the estimated value of the behavior of the shot.
[0053] In step S15, the ball flight of the shot is estimated based
on the target variable calculated in step S14. An example of
contents of the estimated ball flight can be a distance of the shot
in the target line direction (X direction). FIG. 5C shows an
example of the ball flight of the shot in the target line
direction, and a distance from the position X2 to the position X3
indicates a carry (flight distance) and a distance from the
position X3 to a position X4 indicates a run (a rolling distance on
the ground). The distance of the shot may include only the carry or
may be the total value of the carry and the run. An example of
contents of the estimated ball flight can be a deflection of the
shot in the horizontal direction (Y direction). FIG. 5D shows an
example of the ball flight of the shot in the horizontal direction,
in which a position Y1 indicates the initial position (striking
position) of the golf ball 200. A broken line in the X direction
passing through the position Y1 indicates a direction in which the
ball is hit, and a deflection when the ball stops on this line is
set to 0. In the example shown in FIG. 5D, the ball flight is
deflected leftward.
[0054] Referring back to FIG. 6B, in step S16, a golf item suitable
for the golfer is selected as a recommended item based on the
estimated value of the behavior of the shot calculated in step S14
and the ball flight estimated in step S15. The recommended item is,
for example, a golf club or a ball. For the golf club, the
recommended item may be a part such as a shaft or head or a whole
club. As a recommended item, an item having a characteristic that
makes the estimated value of the behavior of the shot closer to a
predetermined reference value (or ideal value), or an item having a
characteristic that makes the ball flight of the shot closer to a
predetermined ideal ball flight is basically selected. If, for
example, the back spin amount or the side spin amount is larger
than an ideal value, an item having a characteristic that
suppresses the back spin amount is selected. If the vertical launch
angle is smaller than an ideal value, an item having a
characteristic that increases the launch angle is selected. If the
deflection of the ball flight in the horizontal direction is large,
an item having a characteristic that suppresses the deflection in
the horizontal direction is selected.
[0055] Information for matching the golf item and the behavior of
the shot or the estimation result of the ball flight is stored in
the storage unit 32, and used to select a recommended item in step
S16. FIG. 7 shows one example, and an example of the information
for selecting a recommended golf ball. In the example shown in FIG.
7, the behavior of the shot is divided into five regions R1 to R5
by setting the vertical launch angle and the back spin amount as
coordinate axes. The region R5 is a region of an ideal behavior
with respect to the vertical launch angle and the back spin amount.
A recommended golf ball corresponding to the region R5 is a product
with standard specifications. The region R1 is a region of a
behavior of a large launch angle and a large back spin amount. The
region R1 is assigned with a golf ball product with specifications
in which the ball is difficult to fly high and the back spin amount
is suppressed, as compared with the product with the standard
specifications.
[0056] The region R2 is a region of a behavior of a small launch
angle and a large back spin amount. The region R2 is assigned with
a golf ball product with specifications in which the ball is easy
to fly high and the back spin amount is suppressed, as compared
with the product with the standard specifications. The region R3 is
a region of a behavior of a large launch angle and a small back
spin amount. The region R3 is assigned with a golf ball product
with specifications in which the ball is difficult to fly high and
the back spin amount is increased, as compared with the product
with the standard specifications. The region R4 is a region of a
behavior of a small launch angle and a small back spin amount. The
region R4 is assigned with a golf ball product with specifications
in which the ball is easy to fly high and the back spin amount is
increased, as compared with the product with the standard
specifications.
[0057] FIGS. 8A and 8B show other examples of information used to
select a recommended item. In an example shown in FIGS. 8A and 8B,
the information shown in FIG. 8A or 8B is selected in accordance
with the initial speed of the shot. For example, if the initial
speed is higher than a threshold, the information shown in FIG. 8A
is selected; otherwise, the information shown in FIG. 8B is
selected.
[0058] In the example shown in FIGS. 8A and 8B, the behavior of the
shot is divided into four regions by setting the vertical launch
angle and the back spin amount as coordinate axes, and
corresponding golf ball products BA to BC are assigned to the
regions, respectively.
[0059] The golf ball product BA is, for example, a golf ball that
has a soft core and a soft cover, and has a characteristic that it
is easy to spin. The golf ball product BB is, for example, a golf
ball that has a soft cover and a hard core, and has a
characteristic that it is easy to spin. The golf ball product BC
is, for example, a golf ball that has a soft core and a hard cover,
and has a characteristic that it is difficult to spin.
[0060] For a golfer whose initial speed of a shot is higher than
the threshold, power to crush the golf ball at the time of striking
is large. In the example shown in FIG. 8A, the region corresponding
to the product BB with the hard core is wide, and the regions
corresponding to the golf ball products BA and BC having the
characteristic that the core is soft are narrow so as not to be
selected easily. Along with increases in launch angle and back spin
amount, the recommended golf ball changes in an order of the
products BA, BB, and BC.
[0061] The example shown in FIG. 8B in which the initial speed is
equal to or lower than the threshold is the same as in FIG. 8A in
that along with increases in launch angle and back spin amount, the
recommended golf ball changes in an order of the products BA, BB,
and BC but is different in that the regions corresponding to the
products BA and BC each having the soft core are wide so the
products are selected easily.
[0062] Referring back to FIG. 6B, in step S17, the information
concerning the golf swing motion of this time is displayed on the
display device 4. Examples of the displayed information are the
values of the explanatory variables used for calculation, the value
of the target variable as a calculation result, the ball flight
estimation result in step S15, and the recommended item in step
S16. Processing of one cycle thus ends.
Second Embodiment
[0063] In the first embodiment, the attributes of the golfer and
those of the golf item have been exemplified as examples of the
explanatory variables. However, a method of selecting one of
arithmetic formulas respectively set for the attributes of a golfer
and those of a golf item without using the attributes of the golfer
and those of the golf item as explanatory variables may be adopted.
FIG. 9 is an explanatory view of arithmetic formulas.
[0064] In an example shown in FIG. 9, each of arithmetic formulas A
and B is generated in accordance with the attribute of a golfer,
and is generated by particularly distinguishing between a male and
a female. The arithmetic formula A is derived from a data group of
a golf swing motion of a male golfer and an actual measured data
group of the behavior of a corresponding shot. The arithmetic
formula B is derived from a data group of a golf swing motion of a
female golfer and an actual measured data group of the behavior of
a corresponding shot.
[0065] In addition, each of arithmetic formulas M and K is
generated in accordance with the attribute of a golf item. Each
arithmetic formula is generated by distinguishing among golf ball
products. The arithmetic formula M is derived from a data group of
a golf swing motion of a golfer using a golf ball product X and an
actual measured data group of the behavior of a corresponding shot.
The arithmetic formula K is derived from a data group of a golf
swing motion of a golfer using a golf ball product Y and an actual
measured data group of the behavior of a corresponding shot.
[0066] In this embodiment, if the processing shown in FIG. 6B is
performed, an input of information (for example, in the example
shown in FIG. 9, a male, a female, or a golf ball product) for
selecting the type of arithmetic formula is accepted in step S11.
In step S12, an arithmetic formula corresponding to the information
input in step S11 is read out. For example, in the case of the
example of FIG. 9, if "male" is input in step S11, the arithmetic
formula A is read out in step S12. If "golf ball product X" is
input in step S11, the arithmetic formula M is read out in step
S12. The subsequent processing is performed in accordance with the
readout type of arithmetic formula.
[0067] Note that distinction of each arithmetic formula shown in
FIG. 9 is merely an example. Each arithmetic formula may be
distinguished and generated only based on the attribute of the
golfer or based on the attribute of the golf item. Alternatively,
each arithmetic formula may be distinguished and generated based on
a combination of the attribute of the golfer and that of the golf
item. An arithmetic formula corresponding to the combination is,
for example, an arithmetic formula X for a male and a golf ball
product A, or an arithmetic formula Z for a female and a golf ball
product A.
[0068] The attribute of the golfer for distinguishing each
arithmetic formula is not limited to the sex, and another attribute
such as the height, weight, length of golf experience, or handicap
may be used. Similarly, the attribute of the golf item for
distinguishing each arithmetic formula is not limited to the golf
ball product, and another attribute such as a golf club product, a
head weight, a shaft flex, the layer structure of a ball, the spin
characteristic of a ball, or the distance characteristic of a ball
may be used.
Third Embodiment
[0069] In the system shown in FIG. 1, the measuring apparatus 2 and
the information processing apparatus 3 are arranged in a relatively
short distance, and the system can be installed in a store or the
like. Another arrangement example can also be adopted. In addition,
a measuring apparatus other than that shown in FIG. 1 can be
adopted.
[0070] FIG. 10 exemplifies another example of the arrangement of an
information processing system 1. In the example of the arrangement
shown in FIG. 10, an information processing apparatus 3 serves as a
server to communicate with a communication apparatus (a mobile
terminal 301, a personal computer 302, or the like) via a network
300. The network 300 is, for example, the Internet.
[0071] An arrangement example EX1 on the measuring side includes
the mobile terminal 301 and a measuring apparatus 2. This system is
suitable for a golfer to individually estimate the behavior of a
shot. The mobile terminal 301 is, for example, a smartphone, and
has a short distance wireless communication function with the
measuring apparatus 2 and a wireless communication function via the
network 300 and a base station (not shown). The mobile terminal 301
transmits, to the information processing apparatus 3, the values of
explanatory variables such as a measurement result received from
the measuring apparatus 2. The information processing apparatus 3
calculates a target variable, and transmits each piece of
information such as ball flight estimation or a recommended item to
the mobile terminal 301. The mobile terminal 301 displays the
received information. That is, the mobile terminal 301 executes
processes in steps S11 and S17 of FIG. 6B, and the information
processing apparatus 3 executes processes in steps S12 to S16 of
FIG. 6B.
[0072] An arrangement example EX2 on the measuring side includes
the personal computer 302 and a plurality of measuring apparatuses
2A. This system is suitable for measuring a golf swing motion in a
golf shop or the like. Each measuring apparatus 2A is an image
capturing apparatus such as a video camera. The personal computer
302 has a processing function for an image captured by each image
capturing 2A, and a wireless communication function via the network
300. A golfer makes a test shot in a test shot box or the like. The
testing golfer is captured from multiple directions by the
plurality of image capturing apparatuses 2A in the test shot box or
the like, thereby capturing the three-dimensional behavior of a
golf club 100. The captured images are loaded into the personal
computer 302 and analyzed, thereby deriving the values of
explanatory variables. Furthermore, the personal computer 302
transmits the values of the explanatory variables to the
information processing apparatus 3. The information processing
apparatus 3 calculates a target variable, and transmits each piece
of information such as ball flight estimation or a recommended item
to the personal computer 302. The personal computer 302 displays
the received information. That is, the personal computer 302
executes the processes in steps S11 and S17 of FIG. 6B, and the
information processing apparatus 3 executes the processes in steps
S12 to S16 of FIG. 6B.
[0073] The invention is not limited to the foregoing embodiments,
and various variations/changes are possible within the spirit of
the invention.
* * * * *